Unmanned aerial vehicle enhanced positioning method and system fusing GNSS and UWB

Abstract

The invention provides an unmanned aerial vehicle enhanced positioning method and system fusing GNSS and UWB, and the method comprises the steps: receiving a flight task instruction from a ground station, starting a GNSS module through the flight task instruction, obtaining an initial position, and building a communication connection with a plurality of fixed beacon nodes through a UWB module; adjusting the position estimation of the unmanned aerial vehicle according to the initial position and the real-time distance measurement information in combination with wide-area positioning data to obtain accurate position estimation, and when the unmanned aerial vehicle enters a signal blocking area, switching to UWB to carry out accurate positioning processing on the unmanned aerial vehicle and generating a fusion positioning result; updating the positioning strategy in case of emergency in the process of executing the specific task to obtain a positioning scheme; all GNSS and UWB positioning data acquired during the flight period are integrated, analyzed and processed to generate a flight path report, and the flight path report is uploaded to a cloud server; according to the technical scheme provided by the invention, the positioning precision and service reliability of the unmanned aerial vehicle in different environments are improved, and smooth completion of tasks is ensured.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of outdoor positioning technology, and in particular to an enhanced positioning method for unmanned aerial vehicles integrating GNSS and UWB. Background Art

[0002] Drones have been widely used in many fields such as modern aviation, logistics distribution, and environmental monitoring. Their positioning accuracy and reliability are crucial to the success of mission execution. Traditional drone positioning mainly relies on the Global Navigation Satellite System (GNSS), such as GPS, which provides drones with a wide range of wide-area positioning services. However, GNSS may encounter signal obstruction or multipath effects in complex environments (such as urban areas with tall buildings or indoors), resulting in reduced positioning accuracy or even complete failure. In addition, in some special application scenarios, the requirements for positioning accuracy are much higher than the standards that GNSS can provide, and traditional technologies are difficult to meet the needs of high-precision positioning.

[0003] Existing UAV positioning solutions usually rely only on GNSS. When the UAV enters an area with blocked signals, it is unable to provide continuous and accurate positioning services, which seriously affects the UAV's mission execution capability and safety. Although some solutions have introduced auxiliary positioning technology, these methods often lack effective integration with GNSS and fail to fully utilize the advantages of different positioning technologies. Therefore, existing technologies have obvious deficiencies in meeting the needs of high-precision positioning in complex environments, especially when real-time adjustment of positioning strategies is required to deal with emergencies. Summary of the invention

[0004] The embodiments of the present invention provide a method and system for enhancing the positioning of unmanned aerial vehicles by integrating GNSS and UWB, so as to solve the obvious deficiencies in the prior art in meeting the requirements of high-precision positioning in complex environments, especially the problem of poor performance when the positioning strategy needs to be adjusted in real time to cope with emergency situations.

[0005] In a first aspect, an embodiment of the present invention provides a method for enhancing positioning of a UAV by integrating GNSS and UWB, comprising: Receiving real-time data streams from different sources, the real-time data streams containing structured data and unstructured data; Receiving a flight mission instruction from a ground station, wherein the flight mission instruction includes a geographic coordinate range and accuracy requirements of a target area; Starting the GNSS module on the UAV and executing the flight mission instruction so that the GNSS module obtains the initial position of the UAV in the target area, and uses the UWB module to establish a communication connection with a plurality of fixed beacon nodes pre-deployed in the target area; According to the initial position and the real-time distance measurement information between the UAV and each fixed beacon node, combined with the wide-area positioning data provided by GNSS, the position estimate of the UAV is dynamically adjusted to obtain a compensated accurate position estimate. According to the compensated accurate position estimate, when the UAV enters a signal-blocked area, the main positioning source is switched to UWB, the UAV is accurately positioned, and a fusion positioning result is generated; When an emergency occurs during the execution of a specific task, the positioning strategy is updated based on the fused positioning result to obtain a positioning solution with an immediate response; After completing the task based on the positioning solution, all GNSS and UWB positioning data acquired during this flight are integrated, the positioning data is analyzed and processed, a flight trajectory report is generated, and the flight trajectory report is uploaded to the cloud server.

[0006] Optionally, according to the initial position and the real-time distance measurement information between the UAV and each fixed beacon node, combined with the wide-area positioning data provided by GNSS, the position estimate of the UAV is dynamically adjusted to obtain a compensated accurate position estimate. According to the compensated accurate position estimate, when the UAV enters a signal-blocked area, the main positioning source is switched to UWB, the UAV is accurately positioned, and a fusion positioning result is generated, including: Using the initial position and the real-time distance measurement information between the UAV and each fixed beacon node, combined with the wide-area positioning data provided by GNSS, the wide-area positioning data is processed by an extended Kalman filter algorithm, a nonlinear state space model is constructed, and a preliminary adjustment is made to the position estimate of the UAV to obtain a preliminary adjusted position estimate; Based on the position estimate after the preliminary adjustment, a particle filter algorithm is used in combination with an adaptive importance sampling strategy to improve the efficiency of the particle filter, and errors caused by multipath effects and satellite occlusion are compensated. At the same time, an environmental perception algorithm is used to evaluate the characteristics of the surrounding environment, and the particle weight distribution is dynamically adjusted to optimize the position estimate, so as to obtain an accurate position estimate after compensation; Based on the accurate position estimation after compensation, when the drone is detected to enter a signal blocked area, the intelligent switching logic is automatically activated to seamlessly switch the main positioning source from GNSS to UWB, and use the graph optimization algorithm to correct the non-line-of-sight error of the UWB ranging data, and combine the anomaly detection algorithm in machine learning to identify and filter out the UWB ranging data that does not meet the preset rules, and generate optimized accurate positioning information; According to the optimized precise positioning information, the best positioning solution in the current environment is predicted by a deep learning model, the dynamic factors of the UAV are calculated, and the time synchronization protocol is adopted, combined with the adaptive clock synchronization algorithm to make the UWB ranging have timestamp accuracy, so as to generate an optimized positioning solution; Based on the optimized positioning scheme, the optimized precise positioning information is fused with the wide-area positioning data, and the credibility of the two positioning sources is calculated using a weighted average method to generate a fused positioning result.

[0007] Optionally, based on the compensated precise position estimation, when the drone is detected to enter a signal-blocked area, the intelligent switching logic is automatically activated to seamlessly switch the main positioning source from GNSS to UWB, and use a graph optimization algorithm to perform non-line-of-sight error correction on the UWB ranging data, and combine the anomaly detection algorithm in machine learning to identify and filter out UWB ranging data that does not meet the preset rules, and generate optimized precise positioning information, including: Based on the accurate position estimation after compensation, when the UAV is detected to enter the signal blocked area, the main positioning source is seamlessly switched from GNSS to UWB using the intelligent switching logic algorithm, and the UWB ranging data is corrected for non-line-of-sight errors using the graph optimization algorithm combined with the multipath effect model to obtain the corrected UWB ranging data; According to the corrected UWB ranging data, combined with the anomaly detection algorithm in machine learning, the UWB ranging data is analyzed in real time, the UWB ranging data that does not meet the preset rules is identified and filtered out, and a deep neural network is used for data classification, and a Bayesian reasoning algorithm is introduced to dynamically adjust the anomaly detection threshold to generate UWB ranging data that has been anomaly detected and filtered; Using an environmental perception algorithm to evaluate the characteristics of the surrounding environment, dynamically adjusting the weight distribution of the UWB ranging data based on the UWB ranging data that has been detected and filtered out by anomalies, and introducing a fuzzy logic system to assign different weight values ​​according to different environmental factors, thereby generating optimized UWB ranging data containing environmental characteristics; Based on the optimized UWB ranging data including environmental characteristics, all UWB ranging data that meet preset rules are integrated, and a genetic algorithm is used for global optimization to find the optimal positioning solution in the UWB ranging data. The positioning result is smoothed by a Kalman filter to eliminate short-term fluctuations and generate optimized precise positioning information.

[0008] Optionally, based on the corrected UWB ranging data, combined with anomaly detection algorithms in machine learning, UWB ranging data is analyzed in real time, UWB ranging data that does not conform to preset rules is identified and filtered out, a deep neural network is used for data classification, and a Bayesian reasoning algorithm is introduced to dynamically adjust anomaly detection thresholds, generating UWB ranging data that has undergone anomaly detection and filtering, including: Using an adaptive threshold setting algorithm, based on the corrected UWB ranging data, real-time analysis of the UWB ranging data is performed to identify data points that do not conform to preset rules, and a Gaussian mixture model is applied to model historical data to predict normal data distribution, assist in the anomaly detection process, and obtain preliminary marked abnormal data points; According to the abnormal data points initially marked, a deep neural network is used, combined with a convolutional neural network to extract spatial features, and a long short-term memory network is used to capture time series characteristics, to classify the UWB ranging data, distinguish normal data from abnormal data, and generate classified UWB ranging data; Based on the classified UWB ranging data, a Bayesian reasoning algorithm is introduced to optimize parameters in combination with a reinforcement learning mechanism, and the Gaussian mixture model parameters are continuously updated in combination with an online learning algorithm, and the threshold of anomaly detection is dynamically adjusted to obtain an optimized anomaly detection result; Based on the optimized anomaly detection results, a confidence scoring mechanism is applied to assign a confidence score to each ranging data point for weight adjustment during reprocessing, and at the same time, data points identified as abnormal are filtered out, and UWB ranging data that meets preset rules is retained, generating UWB ranging data that has undergone anomaly detection and filtering.

[0009] Optionally, the GNSS module integrated in the UAV is started by using the flight mission instruction to obtain the initial position of the UAV in the target area, and a UWB module is used to establish a communication connection with a plurality of fixed beacon nodes pre-deployed in the target area, including: Based on the flight mission instruction, the GNSS module integrated in the UAV is started to process the wide-area positioning data from the GNSS, and the initial position of the UAV in the target area is obtained by combining the data from the IMU inertial measurement unit and calculating through the extended Kalman filter algorithm; Using the initial position, start the UWB module on the drone, use an adaptive frequency control algorithm to optimize the operating frequency of the UWB module, search and select the fixed beacon node with the strongest and most stable signal, confirm the connection status through a two-way handshake protocol, and generate an initialization completion signal; According to the initialization completion signal, the communication quality between the UAV and the fixed beacon node is monitored in real time, the signal strength and delay parameters are evaluated, and the communication connection parameters are dynamically adjusted according to the real-time monitoring results to obtain the dynamically adjusted communication connection parameters; Based on the dynamically adjusted communication connection parameters, an initialization completion signal is generated, indicating that the UAV has successfully obtained an initial position and established a stable communication connection with a fixed beacon node.

[0010] Optionally, according to the fused positioning result, when an emergency situation occurs during the execution of a specific task, the positioning strategy is updated to obtain an immediate response positioning solution, including: Based on the fused positioning result, the flight status of the UAV is monitored in real time to detect whether there is an emergency and obtain an emergency detection result; Based on the emergency detection results, activate the emergency response mechanism, start the rapid assessment process, analyze the current environment and mission requirements, and generate emergency response instructions; Using a mixed integer linear programming algorithm, combined with the current state of the UAV and the emergency response instruction, the optimal flight path of the UAV is calculated again to obtain an updated flight path; Applying a reinforcement learning mechanism to optimize the positioning strategy selection based on the updated flight path and historical data, and generating an optimized positioning strategy; The optimized positioning strategy is integrated to generate an instant response positioning solution, and the positioning solution is immediately applied to the UAV control system.

[0011] Optionally, after completing the task based on the positioning solution, integrating all GNSS and UWB positioning data acquired during the flight, analyzing and processing the positioning data, generating a flight trajectory report, and uploading the flight trajectory report to a cloud server, including: After completing the task based on the positioning solution, collect all GNSS and UWB positioning data acquired during this flight; Using distributed storage technology, the collected positioning data is preliminarily sorted to obtain a sorted positioning data set; According to the collated positioning data set, a data analysis algorithm is applied to analyze the flight path of the UAV in detail to obtain analyzed flight path information; Based on the analyzed flight path information, initially generate a flight trajectory report, the flight trajectory report including: flight time, flight speed, flight altitude and flight route; The initial flight trajectory report is encrypted to generate an encrypted flight trajectory report, and the encrypted flight trajectory report is uploaded to a cloud server using a security protocol.

[0012] In a second aspect, an embodiment of the present invention provides a drone enhanced positioning system integrating GNSS and UWB, including: A receiving module, used for receiving a flight mission instruction from a ground station, wherein the flight mission instruction includes a geographic coordinate range and accuracy requirements of a target area; A start-up module is used to start the GNSS module on the UAV and execute the flight mission instruction so that the GNSS module obtains the initial position of the UAV in the target area and establishes a communication connection with a plurality of fixed beacon nodes pre-deployed in the target area using the UWB module; An adjustment module is used to dynamically adjust the position estimate of the UAV according to the initial position and the real-time distance measurement information between the UAV and each fixed beacon node, combined with the wide-area positioning data provided by GNSS, to obtain a compensated accurate position estimate. According to the compensated accurate position estimate, when the UAV enters a signal-blocked area, the main positioning source is switched to UWB, the UAV is accurately positioned, and a fusion positioning result is generated; An updating module, used to update the positioning strategy according to the fused positioning result and obtain an immediate response positioning solution when an emergency occurs during the execution of a specific task; The generation module is used to integrate all GNSS and UWB positioning data acquired during the flight after completing the task based on the positioning solution, analyze and process the positioning data, generate a flight trajectory report, and upload the flight trajectory report to the cloud server.

[0013] In a third aspect, an embodiment of the present invention provides a computing device, comprising a processor and a memory, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute a method for enhancing the positioning of an unmanned aerial vehicle by integrating GNSS and UWB as described in any one of the first aspects.

[0014] In a fourth aspect, an embodiment of the present invention provides a computer storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement an enhanced positioning method for unmanned aerial vehicle integrating GNSS and UWB as described in any one of the first aspects.

[0015] In an embodiment of the present invention, a flight mission instruction is received from a ground station, wherein the flight mission instruction includes a geographic coordinate range and accuracy requirements of a target area; a GNSS module on a UAV is started to execute the flight mission instruction so that the GNSS module obtains an initial position of the UAV in the target area, and uses a UWB module to establish a communication connection with a plurality of fixed beacon nodes pre-deployed in the target area; based on the initial position and real-time distance measurement information between the UAV and each fixed beacon node, combined with wide-area positioning data provided by GNSS, the position estimation of the UAV is dynamically adjusted to obtain a compensated accurate position estimation; based on the compensated accurate position estimation, when the UAV enters a signal-blocked area, the main positioning source is switched to UWB, and the UAV is The human-machine performs precise positioning processing and generates a fused positioning result; based on the fused positioning result, when an emergency occurs during the execution of a specific task, the positioning strategy is updated to obtain an immediate response positioning solution; after completing the task based on the positioning solution, all GNSS and UWB positioning data acquired during the flight are integrated, the positioning data is analyzed and processed, a flight trajectory report is generated, and the flight trajectory report is uploaded to the cloud server; the technical solution provided by the present invention solves the problem of insufficient positioning accuracy caused by the single reliance on GNSS in the prior art, especially the application limitations in complex environments, and at the same time, by introducing UWB technology and intelligent switching logic, the positioning accuracy and service reliability of the UAV in different environments are improved, ensuring the smooth completion of the task; Furthermore, the extended Kalman filter (EKF) algorithm is used to process the wide-area positioning data provided by GNSS, combined with the data from the IMU inertial measurement unit, to construct a nonlinear state space model and make preliminary adjustments to the drone's position estimate. This method improves the accuracy of the initial position estimate and lays a solid foundation for subsequent optimization; Based on the position estimate after preliminary adjustment, the particle filter algorithm is combined with the adaptive importance sampling strategy to improve the efficiency of the particle filter and compensate for the errors caused by multipath effects and satellite occlusion. At the same time, the environmental perception algorithm is used to evaluate the characteristics of the surrounding environment, dynamically adjust the particle weight distribution, and further optimize the position estimate, greatly improving the robustness and accuracy of the positioning system; When the drone is detected to enter a signal-blocked area, the intelligent switching logic is automatically activated to seamlessly switch the main positioning source from GNSS to UWB. The graph optimization algorithm is used to correct the non-line-of-sight (NLOS) error of the UWB ranging data, and the anomaly detection algorithm in machine learning is combined to identify and filter out UWB ranging data that does not meet the preset rules, generating optimized precise positioning information, ensuring the drone's continuous high-precision positioning capability in signal-blocked areas. Based on the optimized precise positioning information, the deep learning model is used to predict the best positioning solution in the current environment. The dynamic factors of the drone are taken into consideration, and the time synchronization protocol is combined with the adaptive clock synchronization algorithm to ensure the accuracy of the UWB ranging timestamp. This improves the intelligence level of the positioning strategy, allowing the drone to respond and adjust quickly in a changing environment. Based on the optimized positioning scheme, the optimized precise positioning information is fused with the wide-area positioning data, and the weighted average method is used to calculate the credibility of the two positioning sources to generate the final fused positioning result. This fusion method makes full use of the respective advantages of GNSS and UWB to provide more stable and accurate positioning services.

[0016] These and other aspects of the present invention will become more apparent from the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0018] Figure 1 A flowchart of a method for enhancing positioning of a UAV integrating GNSS and UWB provided in an embodiment of the present invention; Figure 2 A schematic diagram of the structure of a UAV enhanced positioning system integrating GNSS and UWB provided in an embodiment of the present invention; Figure 3 A schematic diagram of the structure of a computing device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0020] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0021] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0022] Figure 1 A flowchart of a method for enhancing positioning of a UAV by integrating GNSS and UWB is provided for an embodiment of the present invention. Figure 1 As shown, the method includes: Step 101: receiving a flight mission instruction from a ground station, wherein the flight mission instruction includes a geographic coordinate range and accuracy requirements of a target area; In this step, the flight mission instruction refers to a set of instructions sent by the ground station to the drone, which contains the details of the mission that the drone needs to perform, such as the geographical coordinate range of the target area, accuracy requirements, etc. The geographical coordinate range specifies the specific geographical location that the drone needs to reach or cover, usually expressed in longitude and latitude; the accuracy requirement refers to the requirements for the accuracy of the drone's positioning and navigation, ensuring that the drone can accurately complete the specified mission; The drone receives flight mission instructions from the ground station through the communication module. These instructions include the geographic coordinate range of the target area and the positioning accuracy required for the mission. After the drone analyzes this information, it is ready to start the GNSS module and establish a UWB communication connection.

[0023] Step 102: Start the GNSS module on the UAV and execute the flight mission command so that the GNSS module obtains the initial position of the UAV in the target area and establishes a communication connection with a plurality of fixed beacon nodes pre-deployed in the target area using the UWB module; In this step, GNSS module refers to the Global Navigation Satellite System module, which is used to receive satellite signals and calculate the position of the UAV; initial position refers to the first reliable position calculated by the UAV after receiving a sufficient number of satellite signals; UWB module refers to the Ultra-Wideband module, which is used to perform short-range high-precision ranging with fixed beacon nodes; fixed beacon nodes refer to multiple reference points pre-deployed in the target area to assist the UAV in precise positioning; Based on the information in the flight mission instructions, the GNSS module on the drone is started to obtain its initial position in the target area. At the same time, the UWB module is activated and a communication connection is established with the pre-deployed fixed beacon node to ensure that the drone can receive ranging data from the beacon to provide support for subsequent precise positioning.

[0024] Step 103: According to the initial position and the real-time distance measurement information between the UAV and each fixed beacon node, combined with the wide-area positioning data provided by GNSS, the position estimation of the UAV is dynamically adjusted to obtain a compensated accurate position estimation. According to the compensated accurate position estimation, when the UAV enters a signal-blocked area, the main positioning source is switched to UWB, the UAV is accurately positioned, and a fusion positioning result is generated; In this step, real-time distance measurement information refers to the continuously updated distance information between the UAV and the fixed beacon node; wide-area positioning data refers to the satellite positioning data from GNSS, which provides location information in a large range; accurate position estimation after compensation: more accurate position information obtained after error correction and optimization algorithm processing; fused positioning result refers to the final positioning result generated by combining the advantages of GNSS and UWB technologies.

[0025] In this step, the initial position and the real-time distance measurement information between the UAV and the fixed beacon node, as well as the wide-area positioning data provided by GNSS, are combined, and a filtering algorithm (such as the extended Kalman filter) is used to dynamically adjust the position estimate of the UAV to obtain an accurate position estimate after compensation. When the UAV enters an area where the signal is blocked, it automatically switches the main positioning source to UWB, continues to provide precise positioning services, and generates a fused positioning result.

[0026] Step 104: When an emergency situation occurs during the execution of a specific task, the positioning strategy is updated according to the fused positioning result to obtain a positioning solution with an immediate response; In this step, the fusion positioning result refers to the final positioning result generated by integrating the advantages of GNSS and UWB technologies; the instant response positioning solution refers to the positioning strategy that can be quickly adjusted in response to emergencies, ensuring that the drone can quickly adapt to the changing environment; Based on the fused positioning results, the UAV can immediately update its positioning strategy when encountering an emergency during the execution of a specific mission. It can quickly evaluate the current environment and mission requirements, recalculate the optimal flight path, and apply reinforcement learning mechanisms to optimize the positioning strategy selection. It can generate an instant response positioning solution to ensure the safety of the UAV and mission continuity.

[0027] Step 105: After completing the task based on the positioning solution, integrate all GNSS and UWB positioning data acquired during the flight, analyze and process the positioning data, generate a flight trajectory report, and upload the flight trajectory report to the cloud server; In this step, the flight trajectory report refers to a document that records the flight path, speed, altitude and other key parameters of the drone during the entire mission; the cloud server refers to a data center used to store and manage the flight trajectory report; After the mission is completed, the drone integrates all GNSS and UWB positioning data, analyzes and processes them, and generates a detailed flight trajectory report. The report not only includes key parameters such as flight time, flight speed, flight altitude, flight route, etc., but is also encrypted to protect privacy. Finally, the flight trajectory report is uploaded to the cloud server using a security protocol for subsequent data analysis and mission evaluation.

[0028] Through the above steps, the method of the present invention achieves high-precision and reliable positioning of UAVs in complex environments, especially maintaining good positioning performance in signal-blocked areas. At the same time, it improves the ability of UAVs to respond to emergencies, ensures the safety and continuity of mission execution, and provides strong support for subsequent mission evaluation through detailed flight trajectory reports. In addition, by integrating GNSS and UWB positioning technologies and combining advanced filtering, optimization and learning algorithms, the accuracy, robustness and intelligence level of the UAV positioning system are significantly improved.

[0029] Based on this, the present invention provides a specific embodiment, wherein the step 103 dynamically adjusts the position estimation of the UAV according to the initial position and the real-time distance measurement information between the UAV and each fixed beacon node, combined with the wide-area positioning data provided by GNSS, to obtain a compensated accurate position estimation, and according to the compensated accurate position estimation, when the UAV enters a signal-blocked area, the main positioning source is switched to UWB, the UAV is accurately positioned, and a fusion positioning result is generated, specifically comprising the following steps: Step 201: using the initial position and the real-time distance measurement information between the UAV and each fixed beacon node, combined with the wide-area positioning data provided by GNSS, processing the wide-area positioning data through an extended Kalman filter algorithm, constructing a nonlinear state space model, and preliminarily adjusting the position estimate of the UAV to obtain a preliminarily adjusted position estimate; In this step, wide-area positioning data refers to satellite positioning data from GNSS, which provides location information in a large area; the extended Kalman filter algorithm (EKF) refers to a state estimation method for nonlinear systems that can process noisy input and output signals; the nonlinear state space model refers to a mathematical model used to describe the dynamic characteristics of the system, which is suitable for UAV positioning in complex environments; In this step, the initial position of the UAV and the real-time distance measurement information between it and each fixed beacon node are used in combination with the wide-area positioning data provided by GNSS. The wide-area positioning data is processed by the extended Kalman filter algorithm, and a nonlinear state space model is constructed. The position estimate of the UAV is preliminarily adjusted to obtain the preliminarily adjusted position estimate, which improves the accuracy of the initial position estimate and lays the foundation for subsequent optimization.

[0030] Step 202: Based on the position estimate after the preliminary adjustment, a particle filter algorithm is used in combination with an adaptive importance sampling strategy to improve the efficiency of the particle filter, and errors caused by multipath effects and satellite occlusion are compensated. At the same time, an environment perception algorithm is used to evaluate the surrounding environment characteristics, and the particle weight distribution is dynamically adjusted to optimize the position estimate, so as to obtain a compensated accurate position estimate; In this step, the particle filter algorithm refers to a state estimation technology based on the Monte Carlo method, which is particularly suitable for dealing with nonlinear and non-Gaussian distribution problems; the adaptive importance sampling strategy is a method used to improve the efficiency of particle filtering, dynamically adjusting the sampling weight according to the current environmental characteristics to improve the effectiveness of particle distribution; the multipath effect refers to the error caused by signal reflection or refraction, which affects the positioning accuracy; the environmental perception algorithm is used to evaluate the surrounding environment characteristics (such as building density, terrain undulations, etc.) to help adjust the positioning parameters; the particle weight distribution refers to the probability size represented by each particle, which is used to optimize the position estimation; In this step, based on the position estimate after preliminary adjustment, the particle filter algorithm is combined with the adaptive importance sampling strategy to improve the efficiency of the particle filter, compensate for the errors caused by multipath effects and satellite occlusion, and use the environmental perception algorithm to evaluate the surrounding environment characteristics, dynamically adjust the particle weight distribution, and further optimize the position estimate. Finally, the compensated accurate position estimate is obtained, which significantly improves the robustness and accuracy of the positioning system.

[0031] Step 203: Based on the compensated precise position estimation, when it is detected that the UAV enters a signal-blocked area, the intelligent switching logic is automatically activated to seamlessly switch the main positioning source from GNSS to UWB, and use a graph optimization algorithm to perform non-line-of-sight error correction on the UWB ranging data, and combine the anomaly detection algorithm in machine learning to identify and filter out UWB ranging data that does not meet the preset rules, so as to generate optimized precise positioning information; In this step, the intelligent switching logic is used to automatically determine and switch the mechanism of the main positioning source to ensure that the drone always obtains the most accurate positioning service; the non-line-of-sight error correction is used to correct the ranging error caused by obstacles; the anomaly detection algorithm is used to identify and filter out data points that do not meet the preset rules to ensure the quality of positioning data; Based on the compensated precise position estimation, when the drone is detected entering a signal blocked area, the intelligent switching logic is automatically activated to seamlessly switch the main positioning source from GNSS to UWB, and use the graph optimization algorithm to perform non-line-of-sight error correction on the UWB ranging data. It is combined with the anomaly detection algorithm in machine learning to identify and filter out UWB ranging data that does not meet the preset rules, and generate optimized precise positioning information, ensuring the drone's continuous high-precision positioning capability in complex environments.

[0032] Step 204: Based on the optimized precise positioning information, the best positioning solution in the current environment is predicted by a deep learning model, the dynamic factors of the UAV are calculated, and a time synchronization protocol is adopted, combined with an adaptive clock synchronization algorithm to make the UWB ranging have timestamp accuracy, so as to generate an optimized positioning solution; In this step, the deep learning model refers to a machine learning method based on neural networks, which can extract features from a large amount of data and make predictions; dynamic factors refer to factors that affect the flight path of the drone, such as wind speed, airflow, etc.; the time synchronization protocol is used to ensure the consistency of timestamps between different devices and improve data synchronization and accuracy; the adaptive clock synchronization algorithm is used to dynamically adjust the clock synchronization parameters according to environmental changes to ensure the accuracy of the UWB ranging timestamp; In this step, based on the optimized precise positioning information, the deep learning model is used to predict the best positioning solution in the current environment, taking into account the dynamic factors of the drone. At the same time, the time synchronization protocol is adopted, combined with the adaptive clock synchronization algorithm to make the UWB ranging have timestamp accuracy, so as to generate an optimized positioning solution, improve the intelligence level of the positioning strategy, and enable the drone to respond and adjust quickly in a changing environment.

[0033] Step 205: Based on the optimized positioning solution, the optimized precise positioning information is fused with the wide-area positioning data, and the credibility of the two positioning sources is calculated by weighted average method to generate a fused positioning result; In this step, the weighted average method is used to assign different weights according to the credibility of different data sources to calculate the final result; the fusion positioning result refers to the final positioning result generated by combining the advantages of both GNSS and UWB technologies; Based on the optimized positioning scheme, the optimized precise positioning information is fused with the wide-area positioning data, and the weighted average method is used to calculate the credibility of the two positioning sources to generate the final fused positioning result. This fusion method makes full use of the respective advantages of GNSS and UWB, providing a more stable and accurate positioning service, ensuring that the UAV can obtain the best positioning performance under various environmental conditions.

[0034] Based on this, the present invention provides a specific embodiment, in which step 203, based on the compensated precise position estimation, automatically activates the intelligent switching logic when it is detected that the drone enters a signal blocked area, seamlessly switches the main positioning source from GNSS to UWB, and uses a graph optimization algorithm to perform non-line-of-sight error correction on the UWB ranging data, and combines the anomaly detection algorithm in machine learning to identify and filter out the UWB ranging data that does not meet the preset rules, and generates optimized precise positioning information, which specifically includes the following steps: Step 301: using the initial position and the real-time distance measurement information between the UAV and each fixed beacon node, combined with the wide-area positioning data provided by GNSS, processing the wide-area positioning data through an extended Kalman filter algorithm, constructing a nonlinear state space model, and preliminarily adjusting the position estimate of the UAV to obtain a preliminarily adjusted position estimate; In this step, the initial position of the UAV and the real-time distance measurement information between it and each fixed beacon node are used in combination with the wide-area positioning data provided by GNSS. The wide-area positioning data is processed by the extended Kalman filter algorithm, and a nonlinear state space model is constructed. The position estimate of the UAV is preliminarily adjusted to obtain the preliminarily adjusted position estimate, which improves the accuracy of the initial position estimate and lays the foundation for subsequent optimization.

[0035] Step 302: Based on the position estimate after the preliminary adjustment, a particle filter algorithm is used in combination with an adaptive importance sampling strategy to improve the efficiency of the particle filter, and errors caused by multipath effects and satellite occlusion are compensated. At the same time, an environment perception algorithm is used to evaluate the surrounding environment characteristics, and the particle weight distribution is dynamically adjusted to optimize the position estimate, so as to obtain a compensated accurate position estimate; In this step, based on the position estimate after preliminary adjustment, the particle filter algorithm is combined with the adaptive importance sampling strategy to improve the efficiency of the particle filter, and the errors caused by multipath effects and satellite occlusion are compensated. At the same time, the environmental perception algorithm is used to evaluate the surrounding environment characteristics, dynamically adjust the particle weight distribution, and further optimize the position estimate. Finally, the compensated accurate position estimate is obtained, which improves the robustness and accuracy of the positioning system.

[0036] Step 303: Based on the compensated precise position estimation, when it is detected that the UAV enters a signal-blocked area, the intelligent switching logic is automatically activated to seamlessly switch the main positioning source from GNSS to UWB, and a graph optimization algorithm is used to perform non-line-of-sight error correction on the UWB ranging data, and an anomaly detection algorithm in machine learning is combined to identify and filter out UWB ranging data that does not meet the preset rules, so as to generate optimized precise positioning information; In this step, based on the compensated precise position estimation, when the drone is detected entering a signal blocked area, the intelligent switching logic is automatically activated to seamlessly switch the main positioning source from GNSS to UWB, and use the graph optimization algorithm to perform non-line-of-sight error correction on the UWB ranging data. In combination with the anomaly detection algorithm in machine learning, the UWB ranging data that does not meet the preset rules is identified and filtered out, generating optimized precise positioning information, ensuring the drone's continuous high-precision positioning capability in complex environments.

[0037] Step 304: Based on the optimized precise positioning information, the best positioning solution in the current environment is predicted by a deep learning model, the dynamic factors of the UAV are calculated, and the time synchronization protocol is adopted, combined with an adaptive clock synchronization algorithm to make the UWB ranging have timestamp accuracy, so as to generate an optimized positioning solution; In this step, based on the optimized precise positioning information, the deep learning model is used to predict the best positioning solution in the current environment, taking into account the dynamic factors of the UAV. At the same time, the time synchronization protocol is used, combined with the adaptive clock synchronization algorithm to make the UWB ranging have timestamp accuracy, so as to generate an optimized positioning solution, improve the intelligence level of the positioning strategy, and enable the UAV to respond and adjust quickly in a changing environment.

[0038] Step 305: Based on the optimized positioning solution, the optimized precise positioning information is fused with the wide-area positioning data, and the credibility of the two positioning sources is calculated by weighted average method to generate a fused positioning result; In this step, based on the optimized positioning scheme, the optimized precise positioning information is fused with the wide-area positioning data, and the credibility of the two positioning sources is calculated using the weighted average method to generate the final fused positioning result.

[0039] Based on this, the present invention provides a specific embodiment, wherein step 302, based on the corrected UWB ranging data, combined with anomaly detection algorithms in machine learning, analyzes the UWB ranging data in real time, identifies and filters out UWB ranging data that does not conform to preset rules, and uses a deep neural network to classify data, and introduces a Bayesian reasoning algorithm to dynamically adjust anomaly detection thresholds, generating UWB ranging data that has undergone anomaly detection and filtering, specifically comprising the following steps: Step 401: using an adaptive threshold setting algorithm, based on the corrected UWB ranging data, performing real-time analysis on the UWB ranging data, identifying data points that do not conform to preset rules, applying a Gaussian mixture model to model historical data, predicting normal data distribution, assisting the anomaly detection process, and obtaining preliminary marked abnormal data points; In this step, the adaptive threshold setting algorithm is used to automatically adjust the standard of anomaly detection according to environmental changes to ensure that abnormal data can be accurately identified in different environments; the corrected UWB ranging data refers to the UWB ranging data after non-line-of-sight error correction and other preprocessing steps, which improves the accuracy of the data; the Gaussian mixture model (GMM) refers to a probabilistic model used to model multimodal distributed data and can predict normal data distribution; the preliminarily marked abnormal data points refer to the data points that are preliminarily identified as not meeting the preset rules through analysis and model prediction; In this step, an adaptive threshold setting algorithm is used to perform real-time analysis based on the corrected UWB ranging data to identify data points that do not conform to the preset rules. The Gaussian mixture model is used to model the historical data and predict the normal data distribution to assist the anomaly detection process. Ultimately, preliminary marked abnormal data points are obtained, which improves the flexibility and accuracy of anomaly detection.

[0040] Step 402: Based on the abnormal data points initially marked, a deep neural network is used, combined with a convolutional neural network to extract spatial features, and a long short-term memory network to capture time series characteristics, to classify the UWB ranging data, distinguish normal data from abnormal data, and generate classified UWB ranging data; In this step, deep neural network (DNN) refers to a complex machine learning model that can extract features from large amounts of data and classify them; convolutional neural network (CNN) refers to a neural network structure that is good at extracting spatial features, and is particularly suitable for spatial characteristic analysis of image and ranging data; long short-term memory network (LSTM) refers to a special recursive neural network that is good at capturing long-term dependencies in time series data; classified UWB ranging data refers to the data set generated after distinguishing normal data from abnormal data through deep learning methods; In this step, based on the initially marked abnormal data points, a deep neural network combined with a convolutional neural network is used to extract spatial features, and a long short-term memory network is used to capture time series characteristics. The UWB ranging data is classified and processed to distinguish normal data from abnormal data, and classified UWB ranging data is generated, which enhances the ability to identify abnormal data in complex environments and improves classification accuracy.

[0041] Step 403: Based on the classified UWB ranging data, a Bayesian reasoning algorithm is introduced to optimize parameters in combination with a reinforcement learning mechanism, and the Gaussian mixture model parameters are continuously updated in combination with an online learning algorithm, and the threshold of anomaly detection is dynamically adjusted to obtain an optimized anomaly detection result; In this step, the Bayesian reasoning algorithm refers to a probabilistic reasoning method based on the Bayesian theorem, which is used to dynamically adjust the threshold of anomaly detection; the reinforcement learning mechanism is used to continuously optimize the model parameters through the reward and penalty mechanism to improve the adaptability of the system; the online learning algorithm can continuously update the model parameters during the operation of the system to adapt to the changing environmental conditions; the optimized anomaly detection result refers to the anomaly detection output optimized by the above algorithm, which improves the accuracy and response speed of detection; Based on the classified UWB ranging data, the Bayesian reasoning algorithm is introduced to optimize the parameters in combination with the reinforcement learning mechanism. The Gaussian mixture model parameters are continuously updated in combination with the online learning algorithm. The threshold of anomaly detection is dynamically adjusted to obtain the optimized anomaly detection results, ensuring that the anomaly detection system can adaptively adjust to the optimal state, thereby improving the detection accuracy and response speed.

[0042] Step 404: Based on the optimized anomaly detection result, a confidence score is assigned to each ranging data point using a confidence scoring mechanism for weight adjustment during reprocessing, and data points identified as abnormal are filtered out, and UWB ranging data that meets preset rules is retained, thereby generating UWB ranging data that has undergone anomaly detection and filtering; In this step, the confidence scoring mechanism is used to assign a confidence score to each data point, indicating the possibility that the data point is correctly classified; weight adjustment refers to adjusting the weight of the data point in subsequent processing according to the confidence score to enhance the influence of reliable data; UWB ranging data after anomaly detection and filtering refers to the set of data points that meet the preset rules after anomaly detection and filtering; Based on the optimized anomaly detection results, a confidence scoring mechanism is applied to assign a confidence score to each ranging data point for weight adjustment during reprocessing. At the same time, the data points identified as abnormal are filtered out, and the UWB ranging data that meets the preset rules is retained. The UWB ranging data that has been detected and filtered is generated, ensuring that the ranging data used in the end has a high degree of credibility and improving the overall performance of the positioning system. Based on this, the present invention provides a specific embodiment, wherein the step 102 starts the GNSS module on the UAV and executes the flight mission instruction so that the GNSS module obtains the initial position of the UAV in the target area, and uses the UWB module to establish a communication connection with multiple fixed beacon nodes pre-deployed in the target area, specifically including the following steps: Step 501: Based on the flight mission instruction, the GNSS module integrated in the UAV is started to process the wide-area positioning data from the GNSS, and the initial position of the UAV in the target area is obtained by combining the data from the IMU inertial measurement unit and calculating through the extended Kalman filter algorithm; In this step, MU refers to a combination of built-in sensors used to measure the attitude, velocity, and acceleration of the drone; Extended Kalman Filter (EKF) refers to a state estimation method for nonlinear systems that can handle noisy input and output signals; Based on the information in the flight mission instructions, the GNSS module integrated in the UAV is started to process the wide-area positioning data from the GNSS. Combined with the data from the IMU inertial measurement unit, the extended Kalman filter algorithm is used to calculate the initial position of the UAV in the target area, ensuring that the UAV can obtain preliminary and relatively accurate position information before entering the target area, providing a basis for subsequent precise positioning.

[0043] Step 502: Using the initial position, start the UWB module on the drone, use the adaptive frequency control algorithm to optimize the operating frequency of the UWB module, search and select the fixed beacon node with the strongest and most stable signal, confirm the connection status through the two-way handshake protocol, and generate an initialization completion signal; In this step, UWB module refers to the ultra-wideband (Ultra-Wideband) module, which is used for short-distance high-precision ranging with fixed beacon nodes; the adaptive frequency control algorithm is used to dynamically adjust the operating frequency according to environmental changes and optimize communication performance; fixed beacon nodes refer to multiple reference points pre-deployed in the target area to assist the drone in precise positioning; the two-way handshake protocol refers to a communication confirmation mechanism to ensure that the two devices establish a stable and reliable connection; initialization completion signal: indicates that the drone has successfully completed the initialization of the UWB module and established a stable communication connection; Using the initial position, the UWB module on the drone is started, the operating frequency of the UWB module is optimized using an adaptive frequency control algorithm, and the fixed beacon node with the strongest and most stable signal is searched and selected. The connection status is confirmed through a two-way handshake protocol, and an initialization completion signal is generated, ensuring that the drone can establish a reliable communication connection with the fixed beacon node, preparing for further precise positioning.

[0044] Step 503: According to the initialization completion signal, the communication quality between the UAV and the fixed beacon node is monitored in real time, the signal strength and delay parameters are evaluated, and the communication connection parameters are dynamically adjusted according to the real-time monitoring results to obtain the dynamically adjusted communication connection parameters; In this step, communication quality refers to the reliability of the communication connection, including parameters such as signal strength and delay. Signal strength reflects the amount of energy lost during signal transmission and affects the stability of communication. Delay parameters are used to measure the time difference between sending and receiving, affecting real-time performance and response speed. Communication connection parameters refer to transmission power, data rate, etc., which can be dynamically adjusted to optimize communication performance. According to the initialization completion signal, the communication quality between the UAV and the fixed beacon node is monitored in real time to evaluate the signal strength and delay parameters. According to the real-time monitoring results, the communication connection parameters are dynamically adjusted to obtain the dynamically adjusted communication connection parameters, ensuring that the communication between the UAV and the fixed beacon node is always maintained in the best state, improving the reliability and efficiency of data transmission.

[0045] Step 504: Based on the dynamically adjusted communication connection parameters, an initialization completion signal is generated, indicating that the UAV has successfully obtained an initial position and established a stable communication connection with a fixed beacon node; In this step, the initialization completion signal indicates that the UAV has successfully obtained the initial position and established a stable communication connection with the fixed beacon node; Based on the dynamically adjusted communication connection parameters, an initialization completion signal is finally generated, indicating that the UAV has successfully obtained the initial position and established a stable communication connection with the fixed beacon node. This signal not only marks the successful initialization of the UWB module, but also provides a guarantee for subsequent precise positioning and mission execution.

[0046] Based on this, the present invention provides a specific embodiment, wherein step 104, based on the fused positioning result, when an emergency occurs during the execution of a specific task, updates the positioning strategy to obtain an immediate response positioning solution, specifically comprising the following steps: Step 601: Based on the fusion positioning result, the flight status of the UAV is monitored in real time to detect whether there is an emergency and obtain an emergency detection result; In this step, the flight status refers to dynamic parameters including the speed, acceleration, and direction change rate of the drone; the emergency detection result refers to the identification of whether there is an emergency or abnormal event that requires an immediate response through monitoring the flight status; Based on the fused positioning results, the flight status of the drone is monitored in real time to detect whether there is an emergency. This process includes but is not limited to monitoring the speed, acceleration, direction change rate and other dynamic parameters of the drone to obtain emergency detection results, ensuring that the system can promptly detect and respond to any potential risks or abnormal conditions.

[0047] Step 602: Activate the emergency response mechanism according to the emergency detection result, start the rapid assessment process, analyze the current environment and task requirements, and generate emergency response instructions; In this step, the emergency response mechanism refers to a set of pre-set processes and rules for responding to emergencies; the rapid assessment process is used to quickly analyze the current environment and mission requirements to determine the best course of action; the emergency response instructions refer to specific instructions generated based on the assessment results to guide the drone to take appropriate measures; Based on the emergency detection results, the emergency response mechanism is activated, a rapid assessment process is started, the current environment and mission requirements are analyzed, and emergency response instructions are generated, ensuring that the drone can make the best decision in the shortest time to ensure its safety and mission continuity.

[0048] Step 603: using a mixed integer linear programming algorithm, combined with the current state of the UAV and the emergency response instruction, the optimal flight path of the UAV is calculated again to obtain an updated flight path; In this step, the mixed integer linear programming (MILP) algorithm refers to an optimization method suitable for solving complex problems with discrete variables, which can recalculate the optimal flight path; the updated flight path refers to the new optimized path, which takes into account the changes in the current environment and mission requirements; Using a mixed integer linear programming algorithm, combined with the current state of the UAV and the emergency response instructions, the optimal flight path of the UAV is calculated again to obtain an updated flight path. The safety and efficiency of the new path are ensured through a scientific mathematical model, providing reliable navigation guidance for the UAV.

[0049] Step 604: applying a reinforcement learning mechanism to optimize the positioning strategy selection based on the updated flight path and historical data, and generating an optimized positioning strategy; In this step, the reinforcement learning mechanism refers to a machine learning method that continuously optimizes the strategy selection through a reward and penalty mechanism; the optimized positioning strategy refers to the position estimation and navigation strategy optimized by reinforcement learning, which improves adaptability and accuracy; By applying a reinforcement learning mechanism, the positioning strategy selection is optimized based on the updated flight path and historical data to generate an optimized positioning strategy, which not only takes into account the current mission requirements, but also draws on past experience, further improving the intelligence level and response speed of the positioning system.

[0050] Step 605: synthesizing the optimized positioning strategy, generating an immediate response positioning solution, and immediately applying the positioning solution to the UAV control system; In this step, the immediate response positioning solution refers to the best action guide for the current emergency situation, which can be immediately applied to the drone control system; the drone control system refers to the hardware and software combination responsible for executing all flight commands and control logic; The optimized positioning strategy is integrated to generate an instant response positioning solution, which is immediately applied to the UAV control system, ensuring that the UAV can quickly adjust its behavior in an emergency and perform tasks according to the optimal solution, thereby enhancing the reliability and safety of the UAV control system.

[0051] Based on this, the present invention provides a specific embodiment, wherein step 105 is used to integrate all GNSS and UWB positioning data acquired during the flight after completing the task based on the positioning solution, analyze and process the positioning data, generate a flight trajectory report, and upload the flight trajectory report to a cloud server, and specifically includes the following steps: Step 701: After completing the task based on the positioning solution, collect all GNSS and UWB positioning data acquired during this flight; In this step, the positioning scheme refers to the positioning strategy adopted by the UAV during the mission; the GNSS and UWB positioning data refers to the position information obtained from the Global Navigation Satellite System (GNSS) and Ultra-Wideband (UWB) modules during the entire flight; In this step, after completing the task based on the positioning solution, all GNSS and UWB positioning data acquired during this flight are collected to ensure that all positioning-related data are completely saved, providing a basis for subsequent data analysis.

[0052] Step 702: using distributed storage technology, preliminarily sorting the collected positioning data to obtain a sorted positioning data set; In this step, distributed storage technology refers to a technology that stores data in multiple nodes in a dispersed manner to improve data processing efficiency and reliability; the sorted positioning data set refers to a data set that has been initially sorted, deduplicated, and formatted to facilitate subsequent processing; The collected positioning data are preliminarily sorted out using distributed storage technology to ensure the integrity and consistency of the data, and a sorted positioning data set is obtained. At the same time, duplicate data is removed, timestamps are corrected, etc., to ensure the accuracy of subsequent analysis.

[0053] Step 703: applying a data analysis algorithm to analyze the flight path of the UAV in detail according to the sorted positioning data set to obtain analyzed flight path information; In this step, data analysis algorithm refers to the mathematical model or program used to parse and analyze data, such as time series analysis, spatial distribution analysis, etc.; parsed flight path information refers to the detailed flight path description obtained after processing by the data analysis algorithm, including position changes, speed changes, etc.; Based on the collated positioning data set, a data analysis algorithm is applied to perform a detailed analysis of the UAV's flight path to obtain the analyzed flight path information. By conducting an in-depth analysis of the time series and spatial distribution of the positioning data, the UAV's flight trajectory is reconstructed to provide key information for generating a flight trajectory report.

[0054] Step 704: Based on the analyzed flight path information, initially generate a flight trajectory report, wherein the flight trajectory report includes: flight time, flight speed, flight altitude and flight route; In this step, the flight trajectory report refers to a document that records the key parameters of the drone during the entire mission, such as flight time, flight speed, flight altitude, and flight route; flight time, flight speed, flight altitude, and flight route respectively represent the flight duration, average or instantaneous speed, altitude, and specific flight path of the drone in a specific time period; Based on the analyzed flight path information, a detailed flight trajectory report is generated, which includes but is not limited to key parameters such as flight time, flight speed, flight altitude and flight route. It not only records the mission execution status of the UAV, but also provides valuable data support for subsequent mission evaluation and improvement.

[0055] Step 705: encrypting the initial flight trajectory report to generate an encrypted flight trajectory report, and uploading the encrypted flight trajectory report to a cloud server using a security protocol; In this step, the security protocol refers to HTTPS or SFTP, which ensures the security and integrity of data transmission; the cloud server refers to the data center used to store and manage flight trajectory reports; The flight trajectory report is encrypted to generate a secure flight trajectory report. At the same time, the secure flight trajectory report is uploaded to a cloud server using a secure protocol (such as HTTPS or SFTP), thereby ensuring the secure transmission and long-term storage of the flight trajectory report, and facilitating remote access and subsequent data analysis.

[0056] Figure 2 The present invention provides a structural diagram of a UAV enhanced positioning system integrating GNSS and UWB, such as Figure 2 As shown, the system includes: The receiving module 21 is used to receive a flight mission instruction from a ground station, wherein the flight mission instruction includes a geographic coordinate range and accuracy requirements of a target area; A start module 22 is used to start the GNSS module on the UAV and execute the flight mission instruction so that the GNSS module obtains the initial position of the UAV in the target area and establishes a communication connection with a plurality of fixed beacon nodes pre-deployed in the target area using the UWB module; The adjustment module 23 is used to dynamically adjust the position estimation of the UAV according to the initial position and the real-time distance measurement information between the UAV and each fixed beacon node, combined with the wide-area positioning data provided by the GNSS, to obtain a compensated accurate position estimation. According to the compensated accurate position estimation, when the UAV enters a signal-blocked area, the main positioning source is switched to UWB, the UAV is accurately positioned, and a fusion positioning result is generated; An updating module 24 is used to update the positioning strategy according to the fused positioning result and obtain an immediate response positioning solution when an emergency situation occurs during the execution of a specific task; The generation module 25 is used to integrate all GNSS and UWB positioning data acquired during the flight after completing the task based on the positioning solution, analyze and process the positioning data, generate a flight trajectory report, and upload the flight trajectory report to the cloud server.

[0057] Figure 2 The UAV enhanced positioning system integrating GNSS and UWB can perform Figure 1 The implementation principle and technical effect of the UAV enhanced positioning method integrating GNSS and UWB described in the illustrated embodiment will not be described in detail. The specific manner in which each module and unit performs operations in the UAV enhanced positioning system integrating GNSS and UWB in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0058] In one possible design, Figure 2 The UAV enhanced positioning system integrating GNSS and UWB in the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32; The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0059] The processing component 32 is used to receive a flight mission instruction from a ground station, wherein the flight mission instruction includes a geographic coordinate range and accuracy requirements of a target area; Starting the GNSS module on the UAV and executing the flight mission instruction so that the GNSS module obtains the initial position of the UAV in the target area, and uses the UWB module to establish a communication connection with a plurality of fixed beacon nodes pre-deployed in the target area; According to the initial position and the real-time distance measurement information between the UAV and each fixed beacon node, combined with the wide-area positioning data provided by GNSS, the position estimate of the UAV is dynamically adjusted to obtain a compensated accurate position estimate. According to the compensated accurate position estimate, when the UAV enters a signal-blocked area, the main positioning source is switched to UWB, the UAV is accurately positioned, and a fusion positioning result is generated; When an emergency occurs during the execution of a specific task, the positioning strategy is updated based on the fused positioning result to obtain a positioning solution with an immediate response; After completing the task based on the positioning solution, all GNSS and UWB positioning data acquired during this flight are integrated, the positioning data is analyzed and processed, a flight trajectory report is generated, and the flight trajectory report is uploaded to the cloud server.

[0060] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0061] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0062] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0063] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0064] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0065] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0066] The embodiment of the present invention further provides a computer storage medium storing a computer program, which can achieve the above-mentioned Figure 1 The embodiment shown is a method for enhancing the positioning of a UAV by integrating GNSS and UWB.

[0067] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0068] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0069] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0070] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for enhancing the positioning of unmanned aerial vehicles by integrating GNSS and UWB, characterized in that: include: Receiving a flight mission instruction from a ground station, wherein the flight mission instruction includes a geographic coordinate range and accuracy requirements of a target area; Starting the GNSS module on the UAV and executing the flight mission instruction so that the GNSS module obtains the initial position of the UAV in the target area, and uses the UWB module to establish a communication connection with a plurality of fixed beacon nodes pre-deployed in the target area; According to the initial position and the real-time distance measurement information between the UAV and each fixed beacon node, combined with the wide-area positioning data provided by GNSS, the position estimate of the UAV is dynamically adjusted to obtain a compensated accurate position estimate. According to the compensated accurate position estimate, when the UAV enters a signal-blocked area, the main positioning source is switched to UWB, the UAV is accurately positioned, and a fusion positioning result is generated; When an emergency occurs during the execution of a specific task, the positioning strategy is updated according to the fused positioning result to obtain a positioning solution; After the positioning solution completes the task, all GNSS and UWB positioning data acquired during the flight are integrated, the positioning data is analyzed and processed, a flight trajectory report is generated, and the flight trajectory report is uploaded to the cloud server.

2. The method according to claim 1, characterized in that According to the initial position and the real-time distance measurement information between the UAV and each fixed beacon node, combined with the wide-area positioning data provided by GNSS, the position estimation of the UAV is dynamically adjusted to obtain a compensated accurate position estimation. According to the compensated accurate position estimation, when the UAV enters a signal-blocked area, the main positioning source is switched to UWB, the UAV is accurately positioned, and a fusion positioning result is generated, including: Using the initial position and the real-time distance measurement information between the UAV and each fixed beacon node, combined with the wide-area positioning data provided by GNSS, the wide-area positioning data is processed by an extended Kalman filter algorithm, a nonlinear state space model is constructed, and a preliminary adjustment is made to the position estimate of the UAV to obtain a preliminary adjusted position estimate; Based on the position estimate after the preliminary adjustment, a particle filter algorithm is used in combination with an adaptive importance sampling strategy to improve the efficiency of the particle filter, and errors caused by multipath effects and satellite occlusion are compensated. At the same time, an environmental perception algorithm is used to evaluate the characteristics of the surrounding environment, and the particle weight distribution is dynamically adjusted to optimize the position estimate, so as to obtain an accurate position estimate after compensation; Based on the accurate position estimation after compensation, when the drone is detected to enter a signal blocked area, the intelligent switching logic is automatically activated to seamlessly switch the main positioning source from GNSS to UWB, and use the graph optimization algorithm to correct the non-line-of-sight error of the UWB ranging data, and combine the anomaly detection algorithm in machine learning to identify and filter out the UWB ranging data that does not meet the preset rules, and generate optimized accurate positioning information; According to the optimized precise positioning information, the best positioning solution in the current environment is predicted by a deep learning model, the dynamic factors of the UAV are calculated, and the time synchronization protocol is adopted, combined with the adaptive clock synchronization algorithm to make the UWB ranging have timestamp accuracy, so as to generate an optimized positioning solution; Based on the optimized positioning scheme, the optimized precise positioning information is fused with the wide-area positioning data, and the credibility of the two positioning sources is calculated using a weighted average method to generate a fused positioning result.

3. The method according to claim 2, characterized in that Based on the accurate position estimation after compensation, when the drone is detected to enter a signal blocked area, the intelligent switching logic is automatically activated to seamlessly switch the main positioning source from GNSS to UWB, and use the graph optimization algorithm to correct the non-line-of-sight error of the UWB ranging data, and combine the anomaly detection algorithm in machine learning to identify and filter out the UWB ranging data that does not meet the preset rules, and generate optimized accurate positioning information, including: Based on the accurate position estimation after compensation, when the UAV is detected to enter the signal blocked area, the main positioning source is seamlessly switched from GNSS to UWB using the intelligent switching logic algorithm, and the UWB ranging data is corrected for non-line-of-sight errors using the graph optimization algorithm combined with the multipath effect model to obtain the corrected UWB ranging data; According to the corrected UWB ranging data, combined with the anomaly detection algorithm in machine learning, the UWB ranging data is analyzed in real time, the UWB ranging data that does not meet the preset rules is identified and filtered out, and a deep neural network is used for data classification, and a Bayesian reasoning algorithm is introduced to dynamically adjust the anomaly detection threshold to generate UWB ranging data that has been anomaly detected and filtered; Using an environmental perception algorithm to evaluate the characteristics of the surrounding environment, dynamically adjusting the weight distribution of the UWB ranging data based on the UWB ranging data that has been detected and filtered out by anomalies, and introducing a fuzzy logic system to assign different weight values ​​according to different environmental factors, thereby generating optimized UWB ranging data containing environmental characteristics; Based on the optimized UWB ranging data including environmental characteristics, all UWB ranging data that meet preset rules are integrated, and a genetic algorithm is used for global optimization to find the optimal positioning solution in the UWB ranging data. The positioning result is smoothed by a Kalman filter to eliminate short-term fluctuations and generate optimized precise positioning information.

4. The method according to claim 3, characterized in that According to the corrected UWB ranging data, combined with the anomaly detection algorithm in machine learning, the UWB ranging data is analyzed in real time, and the UWB ranging data that does not meet the preset rules is identified and filtered out. At the same time, a deep neural network is used for data classification, and a Bayesian reasoning algorithm is introduced to dynamically adjust the anomaly detection threshold to generate UWB ranging data after anomaly detection and filtering, including: Using an adaptive threshold setting algorithm, based on the corrected UWB ranging data, real-time analysis of the UWB ranging data is performed to identify data points that do not conform to preset rules, and a Gaussian mixture model is applied to model historical data to predict normal data distribution, assist in the anomaly detection process, and obtain preliminary marked abnormal data points; According to the abnormal data points initially marked, a deep neural network is used, combined with a convolutional neural network to extract spatial features, and a long short-term memory network is used to capture time series characteristics, to classify the UWB ranging data, distinguish normal data from abnormal data, and generate classified UWB ranging data; Based on the classified UWB ranging data, a Bayesian reasoning algorithm is introduced to optimize parameters in combination with a reinforcement learning mechanism, and the Gaussian mixture model parameters are continuously updated in combination with an online learning algorithm, and the threshold of anomaly detection is dynamically adjusted to obtain an optimized anomaly detection result; Based on the optimized anomaly detection result, a confidence scoring mechanism is applied to assign a confidence score to each ranging data point for weight adjustment during reprocessing. At the same time, data points identified as abnormal are filtered out, and UWB ranging data that meets the preset rules is retained to obtain UWB ranging data that has undergone anomaly detection and filtering.

5. The method according to claim 1, characterized in that The GNSS module integrated in the UAV is started by using the flight mission instruction to obtain the initial position of the UAV in the target area, and the UWB module is used to establish a communication connection with multiple fixed beacon nodes pre-deployed in the target area, including: Based on the flight mission instruction, the GNSS module integrated in the UAV is started to process the wide-area positioning data from the GNSS, and the initial position of the UAV in the target area is obtained by combining the data from the IMU inertial measurement unit and calculating through the extended Kalman filter algorithm; Using the initial position, start the UWB module on the drone, use an adaptive frequency control algorithm to optimize the operating frequency of the UWB module, search and select the fixed beacon node with the strongest and most stable signal, confirm the connection status through a two-way handshake protocol, and generate an initialization completion signal; According to the initialization completion signal, the communication quality between the UAV and the fixed beacon node is monitored in real time, the signal strength and delay parameters are evaluated, and the communication connection parameters are dynamically adjusted according to the real-time monitoring results to obtain the dynamically adjusted communication connection parameters; Based on the dynamically adjusted communication connection parameters, an initialization completion signal is generated, where the initialization completion signal is used to indicate that the UAV has successfully obtained an initial position and established a stable communication connection with a fixed beacon node.

6. The method according to claim 1, characterized in that According to the fused positioning result, when an emergency occurs during the execution of a specific task, the positioning strategy is updated to obtain an immediate response positioning solution, including: Based on the fused positioning result, the flight status of the UAV is monitored in real time to detect whether there is an emergency and obtain an emergency detection result; Based on the emergency detection results, activate the emergency response mechanism, start the rapid assessment process, analyze the current environment and mission requirements, and generate emergency response instructions; Using a mixed integer linear programming algorithm, combined with the current state of the UAV and the emergency response instruction, the optimal flight path of the UAV is calculated again to obtain an updated flight path; Applying a reinforcement learning mechanism to optimize the positioning strategy selection based on the updated flight path and historical data, and generating an optimized positioning strategy; The optimized positioning strategy is integrated to generate a positioning solution with immediate response.

7. The method according to claim 1, characterized in that After completing the task based on the positioning solution, integrate all GNSS and UWB positioning data acquired during the flight, analyze and process the positioning data, generate a flight trajectory report, and upload the flight trajectory report to the cloud server, including: After completing the task based on the positioning solution, collect all GNSS and UWB positioning data acquired during this flight; Using distributed storage technology, the collected positioning data is preliminarily sorted to obtain a sorted positioning data set; According to the collated positioning data set, a data analysis algorithm is applied to analyze the flight path of the UAV in detail to obtain analyzed flight path information; Based on the analyzed flight path information, an initial flight trajectory report is generated, wherein the initial flight trajectory report includes: flight time, flight speed, flight altitude and flight route; The initial flight trajectory report is encrypted to generate an encrypted flight trajectory report, and the encrypted flight trajectory report is uploaded to a cloud server using a security protocol.

8. An enhanced positioning system for unmanned aerial vehicles integrating GNSS and UWB, characterized in that: include: A receiving module, used for receiving a flight mission instruction from a ground station, wherein the flight mission instruction includes a geographic coordinate range and accuracy requirements of a target area; A start-up module is used to start the GNSS module on the UAV and execute the flight mission instruction so that the GNSS module obtains the initial position of the UAV in the target area and establishes a communication connection with a plurality of fixed beacon nodes pre-deployed in the target area using the UWB module; An adjustment module is used to dynamically adjust the position estimate of the UAV according to the initial position and the real-time distance measurement information between the UAV and each fixed beacon node, combined with the wide-area positioning data provided by GNSS, to obtain a compensated accurate position estimate. According to the compensated accurate position estimate, when the UAV enters a signal-blocked area, the main positioning source is switched to UWB, the UAV is accurately positioned, and a fusion positioning result is generated; An updating module, used to update the positioning strategy according to the fused positioning result and obtain an immediate response positioning solution when an emergency occurs during the execution of a specific task; The generation module is used to integrate all GNSS and UWB positioning data acquired during the flight after completing the task based on the positioning solution, analyze and process the positioning data, generate a flight trajectory report, and upload the flight trajectory report to the cloud server.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a drone enhanced positioning method integrating GNSS and UWB as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, an enhanced positioning method for a drone integrating GNSS and UWB is implemented as described in any one of claims 1 to 7.

Images